{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T13:36:46Z","timestamp":1787060206304,"version":"build-2736575974"},"reference-count":143,"publisher":"Association for Computing Machinery (ACM)","issue":"11","license":[{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100018870","name":"Poul Due Jensen Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018870","id-type":"DOI","asserted-by":"crossref"}]},{"name":"MADE Digital project"},{"name":"Data Model Convergence (DMC) initiative via the Laboratory Directed Research and Development (LDRD) investments at Pacific Northwest National Laboratory"},{"DOI":"10.13039\/100000993","name":"Battelle Memorial Institute","doi-asserted-by":"crossref","award":["DE-AC05-76RL0-1830"],"award-info":[{"award-number":["DE-AC05-76RL0-1830"]}],"id":[{"id":"10.13039\/100000993","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2023,11,30]]},"abstract":"<jats:p>Dynamical systems see widespread use in natural sciences like physics, biology, and chemistry, as well as engineering disciplines such as circuit analysis, computational fluid dynamics, and control. For simple systems, the differential equations governing the dynamics can be derived by applying fundamental physical laws. However, for more complex systems, this approach becomes exceedingly difficult. Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system. In recent years, there has been an increased interest in applying data-driven modeling techniques to solve a wide range of problems in physics and engineering. This article provides a survey of the different ways to construct models of dynamical systems using neural networks. In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome. Based on the reviewed literature and identified challenges, we provide a discussion on promising research areas.<\/jats:p>","DOI":"10.1145\/3567591","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T08:04:01Z","timestamp":1668585841000},"page":"1-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":125,"title":["Constructing Neural Network Based Models for Simulating Dynamical Systems"],"prefix":"10.1145","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1914-9863","authenticated-orcid":false,"given":"Christian","family":"Legaard","sequence":"first","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9762-2353","authenticated-orcid":false,"given":"Thomas","family":"Schranz","sequence":"additional","affiliation":[{"name":"TU Graz, Graz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0778-5774","authenticated-orcid":false,"given":"Gerald","family":"Schweiger","sequence":"additional","affiliation":[{"name":"TU Graz, Graz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1223-208X","authenticated-orcid":false,"given":"J\u00e1n","family":"Drgo\u0148a","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, WA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9016-8880","authenticated-orcid":false,"given":"Basak","family":"Falay","sequence":"additional","affiliation":[{"name":"AEE\u2013Institute for Sustainable Technologies, Gleisdorf, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2692-9742","authenticated-orcid":false,"given":"Cl\u00e1udio","family":"Gomes","sequence":"additional","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4807-1345","authenticated-orcid":false,"given":"Alexandros","family":"Iosifidis","sequence":"additional","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6220-870X","authenticated-orcid":false,"given":"Mahdi","family":"Abkar","sequence":"additional","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4589-1500","authenticated-orcid":false,"given":"Peter","family":"Larsen","sequence":"additional","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, et\u00a0al. 2016. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. arxiv:1603.04467 (2016)."},{"key":"e_1_3_2_3_2","first-page":"2180","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","author":"Awiszus Maren","year":"2018","unstructured":"Maren Awiszus and Bodo Rosenhahn. 2018. Markov chain neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2180\u20132187."},{"key":"e_1_3_2_4_2","article-title":"Relational inductive biases, deep learning, and graph networks","volume":"1806","author":"Battaglia Peter W.","year":"2018","unstructured":"Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vin\u00edcius Flores Zambaldi, Mateusz Malinowski, et\u00a0al. 2018. Relational inductive biases, deep learning, and graph networks. CoRR abs\/1806.01261 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_5_2","article-title":"Interaction networks for learning about objects, relations and physics","volume":"1612","author":"Battaglia Peter W.","year":"2016","unstructured":"Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, and Koray Kavukcuoglu. 2016. Interaction networks for learning about objects, relations and physics. CoRR abs\/1612.00222 (2016).","journal-title":"CoRR"},{"key":"e_1_3_2_6_2","unstructured":"Atilim Gunes Baydin Barak A. Pearlmutter Alexey Andreyevich Radul and Jeffrey Mark Siskind. 2018. Automatic differentiation in machine learning: A survey. arxiv:1502.05767 [cs stat] (Feb.2018)."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/qua.24890"},{"key":"e_1_3_2_8_2","series-title":"Proceedings of the 36th International Conference on Machine Learning.","first-page":"573","volume":"97","author":"Behrmann Jens","year":"2019","unstructured":"Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, and Joern-Henrik Jacobsen. 2019. Invertible residual networks. In Proceedings of the 36th International Conference on Machine Learning.Proceedings of Machine Learning Research, Vol. 97, Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 573\u2013582."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/3322706.3322734"},{"key":"e_1_3_2_10_2","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop Christopher","year":"2006","unstructured":"Christopher Bishop. 2006. Pattern Recognition and Machine Learning. Springer-Verlag, New York, NY."},{"key":"e_1_3_2_11_2","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","volume":"2104","author":"Bronstein Michael M.","year":"2021","unstructured":"Michael M. Bronstein, Joan Bruna, Taco Cohen, and Petar Velickovic. 2021. Geometric deep learning: Grids, groups, graphs, geodesics, and gauges. CoRR abs\/2104.13478 (2021).","journal-title":"CoRR"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-fluid-010719-060214"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0337-2"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/532288"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/1121743"},{"key":"e_1_3_2_16_2","unstructured":"Bo Chang Lili Meng Eldad Haber Frederick Tung and David Begert. 2018. Multi-level residual networks from dynamical systems view. arxiv:1710.10348 [cs stat] (Feb.2018)."},{"key":"e_1_3_2_17_2","article-title":"A compositional object-based approach to learning physical dynamics","volume":"1612","author":"Chang Michael B.","year":"2016","unstructured":"Michael B. Chang, Tomer Ullman, Antonio Torralba, and Joshua B. Tenenbaum. 2016. A compositional object-based approach to learning physical dynamics. CoRR abs\/1612.00341 (2016).","journal-title":"CoRR"},{"key":"e_1_3_2_18_2","series-title":"Proceedings of the 35th International Conference on Machine Learning.","first-page":"784","volume":"80","author":"Che Zhengping","year":"2018","unstructured":"Zhengping Che, Sanjay Purushotham, Guangyu Li, Bo Jiang, and Yan Liu. 2018. Hierarchical deep generative models for multi-rate multivariate time series. In Proceedings of the 35th International Conference on Machine Learning.Proceedings of Machine Learning Research, Vol. 80, Jennifer Dy and Andreas Krause (Eds.). PMLR, 784\u2013793."},{"key":"e_1_3_2_19_2","unstructured":"Ricky T. Q. Chen Yulia Rubanova Jesse Bettencourt and David Duvenaud. 2019. Neural ordinary differential equations. arxiv:1806.07366 [cs stat] (Dec.2019)."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2017.0387"},{"key":"e_1_3_2_21_2","volume-title":"Advances in Neural Information Processing Systems","author":"Chung Junyoung","year":"2015","unstructured":"Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron C. Courville, and Yoshua Bengio. 2015. A recurrent latent variable model for sequential data. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (Eds.), Vol. 28. Curran Associates."},{"key":"e_1_3_2_22_2","unstructured":"Miles Cranmer Sam Greydanus Stephan Hoyer Peter Battaglia David Spergel and Shirley Ho. 2020. Lagrangian neural networks. arxiv:2003.04630 [physics stat] (July2020)."},{"key":"e_1_3_2_23_2","unstructured":"Raj Dandekar Karen Chung Vaibhav Dixit Mohamed Tarek Aslan Garcia-Valadez Krishna Vishal Vemula and Chris Rackauckas. 2021. Bayesian neural ordinary differential equations. arxiv:2012.07244 [cs] (March2021)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0959-1524(01)00023-3"},{"key":"e_1_3_2_25_2","article-title":"TensorFlow distributions","volume":"1711","author":"Dillon Joshua V.","year":"2017","unstructured":"Joshua V. Dillon, Ian Langmore, Dustin Tran, Eugene Brevdo, Srinivas Vasudevan, Dave Moore, Brian Patton, Alex Alemi, Matthew D. Hoffman, and Rif A. Saurous. 2017. TensorFlow distributions. CoRR abs\/1711.10604 (2017).","journal-title":"CoRR"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.09.001"},{"key":"e_1_3_2_27_2","unstructured":"Jan Drgona Aaron R. Tuor Vikas Chandan and Draguna L. Vrabie. 2020. Physics-constrained deep learning of multi-zone building thermal dynamics. arxiv:2011.05987 [cs.LG] (2020)."},{"key":"e_1_3_2_28_2","unstructured":"Emilien Dupont Arnaud Doucet and Yee Whye Teh. 2019. Augmented neural ODEs. arxiv:1904.01681 [stat.ML] (2019)."},{"key":"e_1_3_2_29_2","unstructured":"Chris Finlay J\u00f6rn-Henrik Jacobsen Levon Nurbekyan and Adam M. Oberman. 2020. How to train your neural ODE: The world of Jacobian and kinetic regularization. arxiv:2002.02798 [stat.ML] (2020)."},{"key":"e_1_3_2_30_2","article-title":"Simplifying Hamiltonian and Lagrangian neural networks via explicit constraints","volume":"2010","author":"Finzi Marc","year":"2020","unstructured":"Marc Finzi, Ke Alexander Wang, and Andrew Gordon Wilson. 2020. Simplifying Hamiltonian and Lagrangian neural networks via explicit constraints. CoRR abs\/2010.13581 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_31_2","unstructured":"Marco Forgione and Dario Piga. 2020. dynoNet: A neural network architecture for learning dynamical systems. arxiv:2006.02250 [cs.LG] (2020)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2008.11.001"},{"key":"e_1_3_2_33_2","unstructured":"Marco Fraccaro S\u00f8ren Kaae S\u00f8nderby Ulrich Paquet and Ole Winther. 2016. Sequential neural models with stochastic layers. arXiv preprint arxiv:1605.07571 (2016)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.4271\/2006-01-1217"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00451"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/356068.356071"},{"key":"e_1_3_2_38_2","unstructured":"Daniel Gedon Niklas Wahlstr\u00f6m Thomas B. Sch\u00f6n and Lennart Ljung. 2020. Deep state space models for nonlinear system identification. arxiv:2003.14162 [eess.SY] (2020)."},{"key":"e_1_3_2_39_2","article-title":"Robust classification using hidden Markov models and mixtures of normalizing flows","volume":"2102","author":"Ghosh Anubhab","year":"2021","unstructured":"Anubhab Ghosh, Antoine Honor\u00e9, Dong Liu, Gustav Eje Henter, and Saikat Chatterjee. 2021. Robust classification using hidden Markov models and mixtures of normalizing flows. CoRR abs\/2102.07284 (2021).","journal-title":"CoRR"},{"key":"e_1_3_2_40_2","article-title":"Neural message passing for quantum chemistry","volume":"1704","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. 2017. Neural message passing for quantum chemistry. CoRR abs\/1704.01212 (2017).","journal-title":"CoRR"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_42_2","first-page":"15379","volume-title":"Advances in Neural Information Processing Systems 32","author":"Greydanus Samuel","year":"2019","unstructured":"Samuel Greydanus, Misko Dzamba, and Jason Yosinski. 2019. Hamiltonian neural networks. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. F. d\u2019Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, 15379\u201315389."},{"key":"e_1_3_2_43_2","unstructured":"Batuhan G\u00fcler Alexis Laignelet and Panos Parpas. 2019. Towards robust and stable deep learning algorithms for forward backward stochastic differential equations. arxiv:1910.11623 [stat.ML] (2019)."},{"key":"e_1_3_2_44_2","article-title":"Learning latent dynamics for planning from pixels","volume":"1811","author":"Hafner Danijar","year":"2018","unstructured":"Danijar Hafner, Timothy P. Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, and James Davidson. 2018. Learning latent dynamics for planning from pixels. CoRR abs\/1811.04551 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-05221-7","volume-title":"Solving Ordinary Differential Equations II: Stiff and Differential-Algebraic Problems","author":"Hairer Ernst","year":"1996","unstructured":"Ernst Hairer and Gerhard Wanner. 1996. Solving Ordinary Differential Equations II: Stiff and Differential-Algebraic Problems. Number 14. Springer-Verlag, Berlin, Germany."},{"key":"e_1_3_2_46_2","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep residual learning for image recognition. arxiv:1512.03385 [cs] (Dec.2015)."},{"key":"e_1_3_2_47_2","unstructured":"Pashupati Hegde Markus Heinonen Harri L\u00e4hdesm\u00e4ki and Samuel Kaski. 2018. Deep learning with differential Gaussian process flows. arxiv:1810.04066 [cs stat] (Oct.2018)."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2008.4811555"},{"key":"e_1_3_2_49_2","article-title":"Neural jump stochastic differential equations","volume":"1905","author":"Jia Junteng","year":"2019","unstructured":"Junteng Jia and Austin R. Benson. 2019. Neural jump stochastic differential equations. CoRR abs\/1905.10403 (2019).","journal-title":"CoRR"},{"key":"e_1_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Weile Jia Han Wang Mohan Chen Denghui Lu Lin Lin Roberto Car Weinan E and Linfeng Zhang. 2020. Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning. arxiv:2005.00223 [physics.comp-ph] (2020).","DOI":"10.1109\/SC41405.2020.00009"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1080\/0144235X.2016.1200347"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10009-013-0289-7"},{"key":"e_1_3_2_53_2","article-title":"Symplectic networks: Intrinsic structure-preserving networks for identifying Hamiltonian systems","volume":"2001","author":"Jin Pengzhan","year":"2020","unstructured":"Pengzhan Jin, Aiqing Zhu, George Em Karniadakis, and Yifa Tang. 2020. Symplectic networks: Intrinsic structure-preserving networks for identifying Hamiltonian systems. CoRR abs\/2001.03750 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_54_2","unstructured":"Laurent Valentin Jospin Wray Buntine Farid Boussaid Hamid Laga and Mohammed Bennamoun. 2020. Hands-on Bayesian neural networks\u2014A tutorial for deep learning users. arxiv:2007.06823 [cs stat] (July2020)."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2720168"},{"key":"e_1_3_2_56_2","unstructured":"Jacob Kelly Jesse Bettencourt Matthew James Johnson and David Duvenaud. 2020. Learning differential equations that are easy to solve. arxiv:2007.04504 [cs.LG] (2020)."},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2005.04.008"},{"key":"e_1_3_2_58_2","unstructured":"Patrick Kidger Ricky T. Q. Chen and Terry Lyons. 2020. \u201cHey that\u2019s not an ODE\u201d: Faster ODE adjoints with 12 lines of code. arxiv:2009.09457 [cs math] (Sept.2020)."},{"key":"e_1_3_2_59_2","unstructured":"Thomas Kipf Ethan Fetaya Kuan-Chieh Wang Max Welling and Richard Zemel. 2018. Neural relational inference for interacting systems. arxiv:1802.04687 [stat.ML] (2018)."},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-12616-5"},{"issue":"3","key":"e_1_3_2_61_2","first-page":"123","article-title":"Quantized-state systems: A DEVS approach for continuous system simulation","volume":"18","author":"Kofman Ernesto","year":"2001","unstructured":"Ernesto Kofman and Sergio Junco. 2001. Quantized-state systems: A DEVS approach for continuous system simulation. Transactions of the Society for Modeling and Simulation International 18, 3 (2001), 123\u2013132.","journal-title":"Transactions of the Society for Modeling and Simulation International"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-38926-0_2"},{"key":"e_1_3_2_63_2","volume-title":"Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI\u201917)","author":"Krishnan R.","year":"2017","unstructured":"R. Krishnan, U. Shalit, and D. Sontag. 2017. Structured inference networks for nonlinear state space models. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI\u201917). 2101\u20132109."},{"key":"e_1_3_2_64_2","unstructured":"Rahul G. Krishnan Uri Shalit and David Sontag. 2015. Deep Kalman filters. arxiv:1511.05121 [stat.ML] (2015)."},{"key":"e_1_3_2_65_2","unstructured":"Rahul G. Krishnan Uri Shalit and David Sontag. 2016. Structured inference networks for nonlinear state space models. arxiv:1609.09869 [stat.ML] (2016)."},{"key":"e_1_3_2_66_2","unstructured":"Rahul G. Krishnan Uri Shalit and David Sontag. 2016. Structured inference networks for nonlinear state space models. arxiv:1609.09869 [cs stat] (Dec.2016)."},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2014.08.034"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0162"},{"key":"e_1_3_2_69_2","volume-title":"Proceedings of the Conference on Robotics: Science and Systems","author":"Lenz I.","year":"2015","unstructured":"I. Lenz, Ross A. Knepper, and A. Saxena. 2015. DeepMPC: Learning deep latent features for model predictive control. In Proceedings of the Conference on Robotics: Science and Systems."},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.5555\/1355322"},{"key":"e_1_3_2_71_2","unstructured":"Xuechen Li Ting-Kam Leonard Wong Ricky T. Q. Chen and David Duvenaud. 2020. Scalable gradients for stochastic differential equations. arxiv:2001.01328 [cs.LG] (2020)."},{"key":"e_1_3_2_72_2","article-title":"Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids","volume":"1810","author":"Li Yunzhu","year":"2018","unstructured":"Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B. Tenenbaum, and Antonio Torralba. 2018. Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. CoRR abs\/1810.01566 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_73_2","article-title":"Propagation networks for model-based control under partial observation","volume":"1809","author":"Li Yunzhu","year":"2018","unstructured":"Yunzhu Li, Jiajun Wu, Jun-Yan Zhu, Joshua B. Tenenbaum, Antonio Torralba, and Russ Tedrake. 2018. Propagation networks for model-based control under partial observation. CoRR abs\/1809.11169 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_74_2","unstructured":"Dong Liu Antoine Honor\u00e9 Saikat Chatterjee and Lars K. Rasmussen. 2019. Powering hidden Markov model by neural network based generative models. arXiv preprint arxiv:1910.05744 (2019)."},{"key":"e_1_3_2_75_2","unstructured":"Xuanqing Liu Tesi Xiao Si Si Qin Cao Sanjiv Kumar and Cho-Jui Hsieh. 2019. Neural SDE: Stabilizing neural ODE networks with stochastic noise. arxiv:1906.02355 [cs.LG] (2019)."},{"key":"e_1_3_2_76_2","unstructured":"Xuanqing Liu Tesi Xiao Si Si Qin Cao Sanjiv Kumar and Cho-Jui Hsieh. 2019. Neural SDE: Stabilizing neural ODE networks with stochastic noise. arxiv:1906.02355 [cs stat] (June2019)."},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.3182\/20060329-3-AU-2901.00009"},{"key":"e_1_3_2_78_2","unstructured":"Michael Lutter Christian Ritter and Jan Peters. 2019. Deep Lagrangian networks: Using physics as model prior for deep learning. arxiv:1907.04490 [cs eess stat] (July2019)."},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1017\/S096249290100006X"},{"key":"e_1_3_2_80_2","unstructured":"Stefano Massaroli Michael Poli Michelangelo Bin Jinkyoo Park Atsushi Yamashita and Hajime Asama. 2020. Stable neural flows. arxiv:2003.08063 [cs.LG] (2020)."},{"key":"e_1_3_2_81_2","unstructured":"Stefano Massaroli Michael Poli Jinkyoo Park Atsushi Yamashita and Hajime Asama. 2021. Dissecting neural ODEs. arxiv:2002.08071 [cs.LG] (2021)."},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619475"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2019.101635"},{"key":"e_1_3_2_84_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"29","author":"Montanez George","year":"2015","unstructured":"George Montanez, Saeed Amizadeh, and Nikolay Laptev. 2015. Inertial hidden Markov models: Modeling change in multivariate time series. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 29."},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.5555\/3374138.3374170"},{"key":"e_1_3_2_86_2","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy Kevin P.","year":"2012","unstructured":"Kevin P. Murphy. 2012. Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge, MA."},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3028-2"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04323-3"},{"key":"e_1_3_2_89_2","unstructured":"Alexander Norcliffe Cristian Bodnar Ben Day Nikola Simidjievski and Pietro Li\u00f2. 2020. On second order behaviour in augmented neural ODEs. arxiv:2006.07220 [cs.LG] (2020)."},{"key":"e_1_3_2_90_2","unstructured":"Viktor Oganesyan Alexandra Volokhova and Dmitry Vetrov. 2020. Stochasticity in neural ODEs: An empirical study. arxiv:2002.09779 [cs stat] (June2020)."},{"key":"e_1_3_2_91_2","unstructured":"Olalekan Ogunmolu Xuejun Gu Steve Jiang and Nicholas Gans. 2016. Nonlinear systems identification using deep dynamic neural networks. arxiv:1610.01439 [cs] (Oct.2016)."},{"key":"e_1_3_2_92_2","article-title":"Nonlinear systems identification using deep dynamic neural networks","volume":"1610","author":"Ogunmolu Olalekan P.","year":"2016","unstructured":"Olalekan P. Ogunmolu, Xuejun Gu, Steve B. Jiang, and Nicholas R. Gans. 2016. Nonlinear systems identification using deep dynamic neural networks. CoRR abs\/1610.01439 (2016).","journal-title":"CoRR"},{"key":"e_1_3_2_93_2","unstructured":"Katharina Ott Prateek Katiyar Philipp Hennig and Michael Tiemann. 2020. When are neural ODE solutions proper ODEs?arxiv:2007.15386 [cs stat] (July2020)."},{"key":"e_1_3_2_94_2","first-page":"8026","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, et\u00a0al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, 8026\u20138037."},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38789-0_11"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-019-09512-8"},{"key":"e_1_3_2_97_2","unstructured":"Michael Poli Stefano Massaroli Junyoung Park Atsushi Yamashita Hajime Asama and Jinkyoo Park. 2020. Graph neural ordinary differential equations. arxiv:1911.07532 [cs.LG] (2020)."},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2019.06.042"},{"key":"e_1_3_2_99_2","first-page":"5241","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Qu Meng","year":"2019","unstructured":"Meng Qu, Yoshua Bengio, and Jian Tang. 2019. GMNN: Graph Markov neural networks. In Proceedings of the International Conference on Machine Learning. 5241\u20135250."},{"key":"e_1_3_2_100_2","unstructured":"Alessio Quaglino Marco Gallieri Jonathan Masci and Jan Koutn\u00edk. 2020. SNODE: Spectral discretization of neural ODEs for system identification. arxiv:1906.07038 [cs.NE] (2020)."},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2987324"},{"key":"e_1_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"e_1_3_2_103_2","unstructured":"Maziar Raissi Paris Perdikaris and George Em Karniadakis. 2018. Multistep neural networks for data-driven discovery of nonlinear dynamical systems. arxiv:1801.01236 [nlin physics:physics stat] (Jan.2018)."},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw4741"},{"key":"e_1_3_2_105_2","first-page":"7785","volume-title":"Advances in Neural Information Processing Systems 31","author":"Rangapuram Syama S.","year":"2018","unstructured":"Syama S. Rangapuram, Matthias W. Seeger, Jan Gasthaus, Lorenzo Stella, Yuyang Wang, and Tim Januschowski. 2018. Deep state space models for time series forecasting. In Advances in Neural Information Processing Systems 31, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.). Curran Associates, 7785\u20137794."},{"key":"e_1_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1029\/2011WR011527"},{"key":"e_1_3_2_107_2","unstructured":"Danilo Jimenez Rezende and Shakir Mohamed. 2016. Variational inference with normalizing flows. arxiv:1505.05770 [stat.ML] (2016)."},{"key":"e_1_3_2_108_2","first-page":"1278","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Rezende Danilo Jimenez","year":"2014","unstructured":"Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic backpropagation and approximate inference in deep generative models. In Proceedings of the International Conference on Machine Learning. 1278\u20131286."},{"key":"e_1_3_2_109_2","unstructured":"David Rolnick Priya L. Donti Lynn H. Kaack Kelly Kochanski Alexandre Lacoste Kris Sankaran Andrew Slavin Ross et\u00a0al. 2019. Tackling climate change with machine learning. arxiv:1906.05433 [cs stat] (Nov.2019)."},{"key":"e_1_3_2_110_2","article-title":"Temporal graph networks for deep learning on dynamic graphs","volume":"2006","author":"Rossi Emanuele","year":"2020","unstructured":"Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael M. Bronstein. 2020. Temporal graph networks for deep learning on dynamic graphs. CoRR abs\/2006.10637 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_111_2","unstructured":"Lars Ruthotto and Eldad Haber. 2018. Deep neural networks motivated by partial differential equations. arxiv:1804.04272 [cs math stat] (Dec.2018)."},{"key":"e_1_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-019-00903-1"},{"key":"e_1_3_2_113_2","article-title":"Hamiltonian graph networks with ODE integrators","volume":"1909","author":"Sanchez-Gonzalez Alvaro","year":"2019","unstructured":"Alvaro Sanchez-Gonzalez, Victor Bapst, Kyle Cranmer, and Peter W. Battaglia. 2019. Hamiltonian graph networks with ODE integrators. CoRR abs\/1909.12790 (2019).","journal-title":"CoRR"},{"key":"e_1_3_2_114_2","article-title":"Learning to simulate complex physics with graph networks","volume":"2002","author":"Sanchez-Gonzalez Alvaro","year":"2020","unstructured":"Alvaro Sanchez-Gonzalez, Jonathan Godwin, Tobias Pfaff, Rex Ying, Jure Leskovec, and Peter W. Battaglia. 2020. Learning to simulate complex physics with graph networks. CoRR abs\/2002.09405 (2020).","journal-title":"CoRR"},{"key":"e_1_3_2_115_2","article-title":"Graph networks as learnable physics engines for inference and control","volume":"1806","author":"Sanchez-Gonzalez Alvaro","year":"2018","unstructured":"Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin A. Riedmiller, Raia Hadsell, and Peter W. Battaglia. 2018. Graph networks as learnable physics engines for inference and control. CoRR abs\/1806.01242 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_2_117_2","article-title":"Nonlinear system identification: A user-oriented roadmap","volume":"1902","author":"Schoukens Johan","year":"2019","unstructured":"Johan Schoukens and Lennart Ljung. 2019. Nonlinear system identification: A user-oriented roadmap. CoRR abs\/1902.00683 (2019).","journal-title":"CoRR"},{"key":"e_1_3_2_118_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.071"},{"key":"e_1_3_2_119_2","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/SSP.166-167.1"},{"key":"e_1_3_2_120_2","unstructured":"Kristof T. Sch\u00fctt Pieter-Jan Kindermans Huziel E. Sauceda Stefan Chmiela Alexandre Tkatchenko and Klaus-Robert M\u00fcller. 2017. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. arxiv:1706.08566 [stat.ML] (2017)."},{"key":"e_1_3_2_121_2","unstructured":"Elliott Skomski Jan Drgona and Aaron Tuor. 2020. Physics-informed neural state space models via learning and evolution. arxiv:2011.13497 [cs.NE] (2020)."},{"key":"e_1_3_2_122_2","doi-asserted-by":"crossref","unstructured":"Elliott Skomski Soumya Vasisht Colby Wight Aaron Tuor Jan Drgona and Draguna Vrabie. 2021. Constrained block nonlinear neural dynamical models. arxiv:2101.01864 [math.DS] (2021).","DOI":"10.23919\/ACC50511.2021.9482930"},{"key":"e_1_3_2_123_2","doi-asserted-by":"publisher","DOI":"10.3182\/20080706-5-KR-1001.01934"},{"key":"e_1_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.01.005"},{"key":"e_1_3_2_125_2","unstructured":"Peter Toth Danilo Jimenez Rezende Andrew Jaegle S\u00e9bastien Racani\u00e8re Aleksandar Botev and Irina Higgins. 2020. Hamiltonian generative networks. arxiv:1909.13789 [cs stat] (Feb.2020)."},{"key":"e_1_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.5017898"},{"key":"e_1_3_2_127_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.9b00181"},{"key":"e_1_3_2_128_2","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2010-28813"},{"key":"e_1_3_2_129_2","unstructured":"Laura von Rueden Sebastian Mayer Katharina Beckh Bogdan Georgiev Sven Giesselbach Raoul Heese Birgit Kirsch et\u00a0al. 2020. Informed machine learning\u2014A taxonomy and survey of integrating knowledge into learning systems. arxiv:1903.12394 [cs stat] (Feb.2020)."},{"key":"e_1_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44584-3_43"},{"key":"e_1_3_2_131_2","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.8b00913"},{"key":"e_1_3_2_132_2","unstructured":"Sifan Wang Yujun Teng and Paris Perdikaris. 2020. Understanding and mitigating gradient pathologies in physics-informed neural networks. arxiv:2001.04536 [cs math stat] (Jan.2020)."},{"key":"e_1_3_2_133_2","unstructured":"Sifan Wang Xinling Yu and Paris Perdikaris. 2020. When and why PINNs fail to train: A neural tangent kernel perspective. arxiv:2007.14527 [cs math stat] (July2020)."},{"key":"e_1_3_2_134_2","unstructured":"G. Wanner and E. Hairer. 1991. Solving Ordinary Differential Equations I: Nonstiff Problems Vol. 1. Springer-Verlag."},{"key":"e_1_3_2_135_2","volume-title":"Advances in Neural Information Processing Systems","author":"Watters Nicholas","year":"2017","unstructured":"Nicholas Watters, Daniel Zoran, Theophane Weber, Peter Battaglia, Razvan Pascanu, and Andrea Tacchetti. 2017. Visual interaction networks: Learning a physics simulator from video. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, 4542\u20134550."},{"key":"e_1_3_2_136_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2019.05.057"},{"key":"e_1_3_2_137_2","unstructured":"Hao Wu Andreas Mardt Luca Pasquali and Frank Noe. 2018. Deep generative Markov state models. arXiv preprint arxiv:1805.07601 (2018)."},{"key":"e_1_3_2_138_2","article-title":"A comprehensive survey on graph neural networks","volume":"1901","author":"Wu Zonghan","year":"2019","unstructured":"Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S. Yu. 2019. A comprehensive survey on graph neural networks. CoRR abs\/1901.00596 (2019).","journal-title":"CoRR"},{"key":"e_1_3_2_139_2","unstructured":"Winnie Xu Ricky T. Q. Chen Xuechen Li and David Duvenaud. 2021. Infinitely deep Bayesian neural networks with stochastic differential equations. arxiv:2102.06559 [cs stat] (Aug.2021)."},{"key":"e_1_3_2_140_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.143001"},{"key":"e_1_3_2_141_2","unstructured":"Linfeng Zhang Jiequn Han Han Wang Wissam A. Saidi Roberto Car and Weinan E. 2018. End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems. arxiv:1805.09003 [physics.comp-ph] (2018)."},{"key":"e_1_3_2_142_2","article-title":"Deep learning on graphs: A survey","volume":"1812","author":"Zhang Ziwei","year":"2018","unstructured":"Ziwei Zhang, Peng Cui, and Wenwu Zhu. 2018. Deep learning on graphs: A survey. CoRR abs\/1812.04202 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_143_2","article-title":"Symplectic ODE-Net: Learning Hamiltonian dynamics with control","volume":"1909","author":"Zhong Yaofeng Desmond","year":"2019","unstructured":"Yaofeng Desmond Zhong, Biswadip Dey, and Amit Chakraborty. 2019. Symplectic ODE-Net: Learning Hamiltonian dynamics with control. CoRR abs\/1909.12077 (2019).","journal-title":"CoRR"},{"key":"e_1_3_2_144_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3567591","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3567591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:51:12Z","timestamp":1750168272000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3567591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,9]]},"references-count":143,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11,30]]}},"alternative-id":["10.1145\/3567591"],"URL":"https:\/\/doi.org\/10.1145\/3567591","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,9]]},"assertion":[{"value":"2021-11-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-04","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}